© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 114586
    Prev
    Next
    INDEX
    Explanations

    GNU General Public License

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     thé
    -0.11
     comed
    -0.11
     Kurt
    -0.10
    pants
    -0.10
    iesta
    -0.10
    ktop
    -0.10
     EDGE
    -0.10
     blockers
    -0.10
     polo
    -0.10
    roma
    -0.09
    POSITIVE LOGITS
     heavier
    0.09
     Gam
    0.09
     Nak
    0.08
     multinational
    0.08
     proximity
    0.07
     thereby
    0.07
     stal
    0.07
    oscope
    0.07
    Cheers
    0.07
     lots
    0.07
    Activations Density 0.001%

    No Known Activations